Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0004

Data Index: 51213 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0549. Min Act: -0.0003

Data Index: 879829 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0004

Data Index: 69091 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0004

Data Index: 807834 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0003

Data Index: 238667 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0003

Data Index: 448114 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0003

Data Index: 267934 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0483. Min Act: -0.0003

Data Index: 425009 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0449. Min Act: -0.0003

Data Index: 669677 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0450. Min Act: -0.0003

Data Index: 794256 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0473. Min Act: -0.0004

Data Index: 71376 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0524. Min Act: -0.0003

Data Index: 781986 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0454. Min Act: -0.0004

Data Index: 752499 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1102112 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0424. Min Act: -0.0003

Data Index: 953503 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0447. Min Act: -0.0003

Data Index: 695427 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1063154 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0440. Min Act: -0.0003

Data Index: 997360 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0447. Min Act: -0.0003

Data Index: 966342 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0446. Min Act: -0.0003

Data Index: 532501 (C4 (Web Text))

Max Activating Token Index: 716